Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already mark this as non-read-only, idempotent, and non-destructive. The description adds valuable context: the operation is additive ('never replacing'), returns the full updated render options, is a paid capability, and imposes the bare https format. This goes beyond the annotations without contradicting them.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Dense but efficient: every sentence contributes distinct value—additive behavior, trigger scenario, approval requirement, format constraint, cost, alternative tool, and return value. Front-loaded with the core purpose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 3-parameter tool with no output schema, the description covers invocation context, constraints, side effects, the alternative tool, and the return value. Nothing essential is missing for an agent to select and call it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and schema descriptions are already decent. The description adds meaningful semantics not in the schema: each origin must be a bare https://host[:port] with no path, and origins are added rather than replacing the existing allowlist. This enhances the agent's ability to construct valid parameters.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource: 'Trust one or more external https origins for a site' while clarifying that it adds to, never replaces, the CSP allowlist. Clearly differentiates the tool's additive scope from replacement via set_render_options.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly says when to use it: as the follow-up when publish_site or update_site reports blocked origins and the owner confirms approval. Also names set_render_options as the alternative for removing or replacing origins, and warns to only pass owner-approved origins.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.